INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     breathe
    0.46
     Shoe
    0.42
    leasing
    0.41
     Deck
    0.40
    (_.
    0.40
    breath
    0.40
    Floating
    0.39
     RDF
    0.39
    frame
    0.38
     manne
    0.38
    POSITIVE LOGITS
     curl
    2.05
    curl
    1.98
     CURL
    1.88
     Curl
    1.85
    Curl
    1.79
     curls
    1.69
     curled
    1.59
     curling
    1.58
     wget
    1.44
    wget
    1.40
    Act Density 0.014%

    No Known Activations